Show simple item record

dc.contributor.authorReddy, Vikas
dc.contributor.authorSanderson, Conrad
dc.contributor.authorSanin, Andres
dc.contributor.authorLovell, Brian C
dc.date.accessioned2021-01-17T23:05:03Z
dc.date.available2021-01-17T23:05:03Z
dc.date.issued2010
dc.identifier.isbn9781424483105
dc.identifier.doi10.1109/avss.2010.84
dc.identifier.urihttp://hdl.handle.net/10072/401179
dc.description.abstractA robust foreground object segmentation technique is proposed, capable of dealing with image sequences containing noise, illumination variations and dynamic backgrounds. The method employs contextual spatial information by analysing each image on an overlapping patch-by-patch basis and obtaining a low-dimensional texture descriptor for each patch. Each descriptor is passed through an adaptive multi-stage classifier, comprised of a likelihood evaluation, an illumination robust measure, and a temporal correlation check. A probabilistic foreground mask generation approach integrates the classification decisions by exploiting the overlapping of patches, ensuring smooth contours of the foreground objects as well as effectively minimising the number of errors. The parameter settings are robust against wide variety of sequences and post-processing of foreground masks is not required. Experiments on the difficult Wallflower and I2R datasets show that the proposed method obtains considerably better results (both qualitatively and quantitatively) than methods based on Gaussian mixture models, feature histograms, and normalised vector distances. Further experiments on the CAVIAR dataset (using several tracking algorithms) indicate that the proposed method leads to considerable improvements in object tracking accuracy.
dc.publisherIEEE
dc.relation.ispartofconferencename2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
dc.relation.ispartofconferencetitle2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance
dc.relation.ispartofdatefrom2010-08-29
dc.relation.ispartofdateto2010-09-01
dc.relation.ispartoflocationBoston, USA
dc.relation.ispartofpagefrom172
dc.relation.ispartofpageto179
dc.titleAdaptive Patch-Based Background Modelling for Improved Foreground Object Segmentation and Tracking
dc.typeConference output
dcterms.bibliographicCitationReddy, V; Sanderson, C; Sanin, A; Lovell, BC, Adaptive Patch-Based Background Modelling for Improved Foreground Object Segmentation and Tracking, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance, 2010, pp. 172-179
dc.date.updated2021-01-17T23:02:40Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© 2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
gro.hasfulltextFull Text
gro.griffith.authorSanderson, Conrad


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record